Scan-level report labelling on Spondylolisthesis (test)
97.4Balanced AccuracyDirect Query
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Direct QueryQuery Model=GPT-42024.10 | 97.4 | — | — | 97.3 | |
| Direct QueryQuery Model=Zephyr2024.10 | 97.4 | 0.026 | 0.996 | 97.4 | |
| Direct QueryQuery Model=Llama32024.10 | 97.4 | 0.026 | 0.993 | 97.4 | |
| Summary-QuerySummary Model=Llama3, Query Model=Llama32024.10 | 97.4 | 0.026 | 0.994 | 97.4 | |
| Summary-QuerySummary Model=Z-SFT, Query Model=Zephyr2024.10 | 94.8 | 0.026 | 0.984 | 94.6 | |
| Summary-QuerySummary Model=Zephyr, Query Model=Zephyr2024.10 | 94.2 | 0.023 | 0.985 | 93.8 |